Mismatched image identification using histogram of loop closure error for feature-based optical mapping

Armagan Elibol, Nak Young Chong, Hyunjung Shim, Jinwhan Kim, Nuno Gracias, Rafael Garcia

Research output: Contribution to journalArticlepeer-review


Image registration is one of the most fundamental steps in optical mapping from mobile platforms. Lately, image registration is performed by detecting salient points in two images and matching their descriptors. Robust methods [such as Random Sample Consensus (RANSAC)] are employed to eliminate outliers and compute the geometric transformation between the coordinate frames of images, typically a homography when the images contain views of a flat area. However, the image registration pipeline can sometimes provide a sufficient number of wrong inliers within the error bounds even when images do not overlap at all. Such mismatches occur especially when the scene has repetitive texture and shows structural similarity. Such pairs prevent the trajectory (thus, a mosaic) from being estimated accurately. In this paper, we propose to utilize closed-loop constraints for identifying mismatches. Cycles appear when the camera revisits an area that was imaged before, which is a common practice especially for mapping purposes. The proposed method exploits the fact that images forming a cycle should have an identity mapping when all the homographies between images in the cycle are multiplied. Our proposal obtains error statistics for each matched image pair extracting several cycle bases. Then, by using a previously trained classifier, it identifies image pairs by comparing error histograms. We present experimental results with different image sequences.

Original languageEnglish
Pages (from-to)196-206
Number of pages11
JournalInternational Journal of Intelligent Robotics and Applications
Issue number2
Publication statusPublished - 2019 Jun 1

Bibliographical note

Funding Information:
This research was partially supported by the Spanish National Project UDRONE (Robot submarino inteligente para la exploracion omnidireccional e inmersiva del bentos) CTM2017-83075-R, the EU VII Framework Programme as part of the Eurofleets2 (Grant Number FP7-INF-2012-312762) and by the MIST (Ministry of Science and ICT), Rep.of Korea, under the ICT Consilience Creative Program (IITP-2018-2017-0-01015) supervised by the IITP (Institute of Information & Communications Technology Planning & Evaluation) 1 In an undirected graph G , two vertices u and v are called connected if G contains a path from u to v . A graph is said to be connected if every pair of vertices in the graph is connected. 2 Dataset was obtained from http://www.soe.ucsc.edu/~davis/panorama/ . 3 The dataset is obtained from www.diegm.uniud.it/fusiello/demo/hrm/ .

Publisher Copyright:
© 2019, Springer Nature Singapore Pte Ltd.

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Artificial Intelligence


Dive into the research topics of 'Mismatched image identification using histogram of loop closure error for feature-based optical mapping'. Together they form a unique fingerprint.

Cite this